Autors: Marinova, I. I., Mateev, V. M.
Title: Machine Learning Approach for Particle Kinetics Modeling
Keywords: FeO, LSTM network, machine learning, magnetic field, modeling, nano particle, particle kinetics

Abstract: In this work is presented numerical modeling of magnetic particle kinetics in outer magnetic fieldby FDM method and machine learning approach. Particle dynamics method is performed by nodal solver, based on first order finite difference method, with step-wise transient collision estimator and static outer magnetic field gradient intensity force correction. Magnetic field distribution is modeled independently of particle dynamics by Biot-Savart method. Further, a machine learning approach based on LSTM network is trained for particle trajectory modeling. Consideration on network parameters is made for the particular modeling task for Fe2O3 particles convective kinetics.

References

  1. I. Marinova and V. Mateev, "Thermo-Electro-Magnetic Convection in Electrically Conductive Ferrofluids," 2019 22nd International Conference on the Computation of Electromagnetic Fields (COMPUMAG), Paris, France, 2019, pp. 1-4, doi: 10.1109/COMPUMAG45669.2019.9032802.
  2. V. Mateev, I. Marinova and Y. Saito, "Coupled Field Modeling of Ferrofluid Heating in Tumor Tissue," in IEEE Transactions on Magnetics, vol. 49, no. 5, pp. 1793-1796, May 2013, doi: 10.1109/TMAG.2013.2242441.
  3. D. J. Larson and D. W. Hewett, "Complex Particle Kinetics: Particle Interactions Over the Full Range of Collisionality," 2007 IEEE 34th International Conference on Plasma Science (ICOPS), Albuquerque, NM, USA, 2007, pp. 694-694, doi: 10.1109/PPPS.2007.4346000.
  4. M. R. U. Rahman, T. J. Kwak, J. C. Woehl and W. -J. Chang, "Characterization of stiffness of micro-particle trapped in dielectrophoretic-microfluidic device," 2020 2nd International Conference on Advanced Information and Communication Technology (ICAICT), Dhaka, Bangladesh, 2020, pp. 94-98, doi: 10.1109/ICAICT51780.2020.9333521.
  5. C. Wang, L. Ma, R. Li, T. S. Durrani and H. Zhang, "Exploring Trajectory Prediction Through Machine Learning Methods," in IEEE Access, vol. 7, pp. 101441-101452, 2019, doi: 10.1109/ACCESS.2019.2929430.
  6. S. Markidis, I. Peng, A. Podobas, I. Jongsuebchoke, G. Bengtsson and P. Herman, "Automatic Particle Trajectory Classification in Plasma Simulations," 2020 IEEE/ACM Workshop on Machine Learning in High Performance Computing Environments (MLHPC) and Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (AI4S), GA, USA, 2020, pp. 64-71, doi: 10.1109/MLHPCAI4S51975.2020.00014.
  7. A. A. Santos, S. Kar, J. M. F. Moura and J. Xavier, "Thermodynamic limit of interacting particle systems over dynamical networks," 2016 50th Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, USA, 2016, pp. 997-1000, doi: 10.1109/ACSSC.2016.7869517.

Issue

8th International Symposium on Innovative Approaches in Smart Technologies, ISAS 2024 - Proceedings, pp. 1-4, 2024, , https://doi.org/10.1109/ISAS64331.2024.10845576

Copyright IEEE

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus